Open-Assistant / oasst-model-evalLinks
Evaluation of the Open-Assistant language models
☆29Updated 6 months ago
Alternatives and similar repositories for oasst-model-eval
Users that are interested in oasst-model-eval are comparing it to the libraries listed below
Sorting:
- Multipack distributed sampler for fast padding-free training of LLMs☆204Updated last year
- Multi-Domain Expert Learning☆67Updated 2 years ago
- OpenAlpaca: A Fully Open-Source Instruction-Following Model Based On OpenLLaMA☆304Updated 2 years ago
- Code repository for the c-BTM paper☆108Updated 2 years ago
- Comprehensive analysis of difference in performance of QLora, Lora, and Full Finetunes.☆83Updated 2 years ago
- ☆94Updated 2 years ago
- Reimplementation of the task generation part from the Alpaca paper☆119Updated 2 years ago
- A bagel, with everything.☆326Updated last year
- ☆95Updated 2 years ago
- Exploring finetuning public checkpoints on filter 8K sequences on Pile☆116Updated 2 years ago
- ☆416Updated 2 years ago
- Experiments on speculative sampling with Llama models☆128Updated 2 years ago
- Open Instruction Generalist is an assistant trained on massive synthetic instructions to perform many millions of tasks☆209Updated 2 years ago
- ☆457Updated 2 years ago
- Drop in replacement for OpenAI, but with Open models.☆156Updated 2 years ago
- batched loras☆349Updated 2 years ago
- QLoRA: Efficient Finetuning of Quantized LLMs☆79Updated last year
- Notus is a collection of fine-tuned LLMs using SFT, DPO, SFT+DPO, and/or any other RLHF techniques, while always keeping a data-first app…☆169Updated 2 years ago
- ModuleFormer is a MoE-based architecture that includes two different types of experts: stick-breaking attention heads and feedforward exp…☆226Updated 4 months ago
- Command-line script for inferencing from models such as MPT-7B-Chat☆100Updated 2 years ago
- Inference code for Mistral and Mixtral hacked up into original Llama implementation☆371Updated 2 years ago
- inference code for mixtral-8x7b-32kseqlen☆105Updated 2 years ago
- ☆380Updated 2 years ago
- Used for adaptive human in the loop evaluation of language and embedding models.☆308Updated 2 years ago
- Inference code for Persimmon-8B☆412Updated 2 years ago
- GPTQLoRA: Efficient Finetuning of Quantized LLMs with GPTQ☆101Updated 2 years ago
- The GeoV model is a large langauge model designed by Georges Harik and uses Rotary Positional Embeddings with Relative distances (RoPER).…☆121Updated 2 years ago
- Merge Transformers language models by use of gradient parameters.☆213Updated last year
- Experiments with generating opensource language model assistants☆97Updated 2 years ago
- A crude RLHF layer on top of nanoGPT with Gumbel-Softmax trick☆294Updated 2 years ago